Using a genetic algorithm-based RAROC model for the performance and persistence of the funds

Assisting fund investors in making better investment decisions when faced with market climate change is an important subject. For this purpose, we adopt a genetic algorithm (GA) to search for an optimal decay factor for an exponential weighted moving average model, which is used to calculate the value at risk combined with risk-adjusted return on capital (RAROC). We then propose a GA-based RAROC model. Next, using the model we find the optimal decay factor and investigate the performance and persistence of 31 Taiwanese open-end equity mutual funds over the period from November 2006 to October 2009, divided into three periods: November 2006–October 2007, November 2007–October 2008, and November 2008–October 2009, which includes the global financial crisis. We find that for three periods, the optimal decay factors are 0.999, 0.951, and 0.990, respectively. The rankings of funds between bull and bear markets are quite different. Moreover, the proposed model improves performance persistence. That is, a fund's past performance will continue into the future.     

Restricted most powerful Bayesian tests for linear models

Uniformly most powerful Bayesian tests (UMPBTs) are a new class of Bayesian tests in which null hypotheses are rejected if their Bayes factor exceeds a specified threshold. The alternative hypotheses in UMPBTs are defined to maximize the probability that the null hypothesis is rejected. Here, we generalize the notion of UMPBTs by restricting the class of alternative hypotheses over which this maximization is performed, resulting in restricted most powerful Bayesian tests (RMPBTs). We then derive RMPBTs for linear models by restricting alternative hypotheses to g priors. For linear models, the rejection regions of RMPBTs coincide with those of usual frequentist F‐tests, provided that the evidence thresholds for the RMPBTs are appropriately matched to the size of the classical tests. This correspondence supplies default Bayes factors for many common tests of linear hypotheses. We illustrate the use of RMPBTs for ANOVA tests and t‐tests and compare their performance in numerical studies.     

Test for Trend With a Multinomial Outcome

ABSTRACT

There is no established procedure for testing for trend with nominal outcomes that would provide both a global hypothesis test and outcome-specific inference. We derive a simple formula for such a test using a weighted sum of Cochran–Armitage test statistics evaluating the trend in each outcome separately. The test is shown to be equivalent to the score test for multinomial logistic regression, however, the new formulation enables the derivation of a sample size formula and multiplicity-adjusted inference for individual outcomes. The proposed methods are implemented in the R package multiCA.     

A new approach for the genetic algorithm

This paper proposes a new approach based on two explicit rules of Mendel experiments and Mendel's population genetics for the genetic algorithm (GA). These rules are the segregation and independent assortment of alleles, respectively. This new approach has been simulated for the optimization of certain test functions. The doctrinal sense of GA is conceptually improved by this approach using a Mendelian framework. The new approach is different than the conventional one in terms of crossover, recombination, and mutation operators. The results obtained here are in agreement with those of the conventional GA, and even better in some cases. These results suggest that the new approach is overall more sensitive and accurate than the conventional one. Possible ways of improving the approach by including more genetic formulae in the code are also discussed.     

Evaluating lifetime performance for the Pareto model with censored and imprecise information

A lifetime capability index L _tp has been proposed to measure the business lifetime performance, wherein output lifetime measurements are assumed to be precise from the Pareto model with censored information. In the present study, we study a more realistic situation where the lifetime output data are imprecise. The approach developed by Buckley [Fuzzy system, Soft Comput. 9 (2005), pp. 757–760; Fuzzy statistics: Regression and prediction, Soft Comput. 9 (2005), pp. 769–775] incorporated with some extensions (a set of confidence intervals, one on top of the other), is used to construct the triangular-shaped fuzzy number for the fuzzy estimate of the L _tp. With the sampling distribution of the unbiased estimator of the L _tp, two useful fuzzy inference criteria, its critical value and fuzzy p-value are obtained to assess the lifetime performance. The presented methodology can handle the lifetime performance assessment on the condition that sample lifetime data are involved with imprecise information, classifying the lifetime performance with the three-decision rule. With different preset requirements and a certain degree of imprecise data, we also develop a four quadrants decision-making plot where managers can easily simultaneously visualize several important features of lifetime performance for making a decision. An example of business lifetime data is given to illustrate the applicability of the proposed method.     

Power and stability comparisons of multiple testing procedures with false discovery rate control

High-throughput data analyses are widely used for examining differential gene expression, identifying single nucleotide polymorphisms, and detecting methylation loci. False discovery rate (FDR) has been considered a proper type I error rate to control for discovery-based high-throughput data analysis. Various multiple testing procedures have been proposed to control the FDR. The power and stability properties of some commonly used multiple testing procedures have not been extensively investigated yet, however. Simulation studies were conducted to compare power and stability properties of five widely used multiple testing procedures at different proportions of true discoveries for various sample sizes for both independent and dependent test statistics. Storey's two linear step-up procedures showed the best performance among all tested procedures considering FDR control, power, and variance of true discoveries. Leukaemia and ovarian cancer microarray studies were used to illustrate the power and stability characteristics of these five multiple testing procedures with FDR control.     

简析社会学理论检验中的演绎方法

通过介绍和分析社会学中的演绎逻辑,提出演绎逻辑在社会学理论检验过程中具有假设推演的重要作用,这同它在自然科学中扩充知识的功能不同。社会学中的演绎逻辑具有逻辑演绎和经验演绎两种类型,它们具有各自的优点及不足,因此在社会学理论检验过程中应将两者有机结合,扬长避短。     

非均匀分布式星载雷达栅瓣抑制技术研究

分布式星载雷达突破了单星雷达受功率孔径积的限制,具有更远的探测距离;突破了单星雷达受天线基线长度的限制,具有更窄的波束宽度,但是会产生较多的孔径干涉栅瓣.文中研究了一种分布式星载雷达的栅瓣抑制方法,该方法采用遗传算法来确定超稀疏的非均匀分布式星载雷达阵列的位置矢量,利用个体的实值编码提高了遗传算法的计算效率.＃在给定卫星阵列基线长度和卫星间最小间距约束的条件下,通过仿真实验验证了该方法抑制栅瓣的有效性.卫星个数越多,栅瓣抑制效果越好.随着小卫星技术的发展以及小卫星成本的降低,文中基于非均匀分布阵列的栅瓣抑制方法对小卫星的分布设计具有一定的参考价值.     

现代生物技术的宣传与普及：科学家的职责——在国内首次生物技术与现代农业科普与传播研讨会上的讲话

与转基因相关的现代生物技术等科学问题以及如何对公众进行科普宣传等问题,已引起人们的高度关注。作为科学家应该向公众、向政策的制定者来传播科学家自身关注和从事的科学问题;应该加强对科学家、公众及大众媒体、政府的政策制定者三者关系的认识、交流与沟通,及时解决出现的问题。转基因技术与传统育种技术是一脉相承的,其本质都是通过获得优良基因对作物进行遗传改良。科学家在进行相关研究时必须遵守相应的科学伦理规范和相应的科学准则,必须严格自律。科学家要通过推动一系列的研讨和合作,探求相关重要问题的解决方案,增强政府官员和公众对植物科学在解决这些问题上重要性的认识,使全社会的公众来关注今天的植物科学和农业给未来的人类以及我们的地球所产生的影响。